LAVA: Logic-Aware Validation and Augmentation Framework for Large-Scale Financial Document Auditing

Abstract:Financial document validation in production, such as payroll auditing, tax compliance, and loan underwriting, demands exceptional accuracy, consistency, and reproducibility under strict enterprise constraints. In practice, documents arrive with heterogeneous layouts and formats, semantically rich and context-dependent content, and embedded business rules that current pipelines struggle to process reliably. We introduce LAVA (Logic-Aware Validation and Augmentation), a modular, backbone-agnostic pipeline built on multimodal large language models, that integrates a four-stage design: document-rule retrieval, layout-preserving information extraction, auxiliary metadata enrichment, and auditable symbolic/arithmetic verification. LAVA supports robust rule grounding, fine-grained error attribution, and consistent, traceable end-to-end execution, capabilities essential for high-stakes deployment. Evaluated on a large real-world benchmark with diverse financial documents and dozens of expert-curated validation rules, LAVA outperforms baselines in hallucination control and edge-case handling while maintaining efficient token usage, demonstrating practicality for high-volume, time-critical validation.

Artificial Intelligence (cs.AI)

arXiv:2608.16763 [cs.AI]

(or arXiv:2608.16763v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2608.16763 arXiv-issued DOI via DataCite (pending registration)

Proceedings of The 10th Workshop on Financial Technology and Natural Language Processing (FinNLP 2025), Association for Computational Linguistics, pp. 75-92, 2025

https://doi.org/10.18653/v1/2025.finnlp-2.7 DOI(s) linking to related resources